2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)最新文献

筛选
英文 中文
Improved multi-view depth estimation for view synthesis in 3D video coding 改进的多视点深度估计,用于3D视频编码中的视点合成
Qiuwen Zhang, P. An, Yan Zhang, Liquan Shen, Zhaoyang Zhang
{"title":"Improved multi-view depth estimation for view synthesis in 3D video coding","authors":"Qiuwen Zhang, P. An, Yan Zhang, Liquan Shen, Zhaoyang Zhang","doi":"10.1109/3DTV.2011.5877185","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877185","url":null,"abstract":"Multi-view depth estimation is an important part in the virtual view synthesis and depth map coding within the 3DV/FTV applications. However, existing depth estimation methods generally have difficulty to generate good depth results around object edges or in areas with less texture. To solve this problem, we propose an improved algorithm to obtain a smooth and accurate depth map for view synthesis in 3D video coding. The proposed method aims to preserve details in the depth map and simultaneously smooth depths in object boundary occluded area, less texture and discontinuity regions, to avoid blurring in the synthesized views. Experimental results show a significant improvement of the initial input depth maps and coding efficiency, as well as a reduction of view synthesis artifacts.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123926284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Evaluation of view synthesis algorithms for mobile 3DTV 移动3DTV视图合成算法评价
G. Tech, K. Muller, T. Wiegand
{"title":"Evaluation of view synthesis algorithms for mobile 3DTV","authors":"G. Tech, K. Muller, T. Wiegand","doi":"10.1109/3DTV.2011.5877218","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877218","url":null,"abstract":"View synthesis algorithms suitable for mobile devices are presented and discussed. The focus is on low complexity rendering methods that enable line wise processing. A full pixel accurate rendering algorithm is compared to two algorithms using sub pixel accuracy: One sub pixel accurate method applies a linear interpolation, while the other method utilizes rendering in an up-sampled domain. An analysis of the rendered views and the corresponding stereo views is given. In the evaluation especially aspects on 3D impression, hole filling in disoccluded areas and flickering were investigated. Finally, optimized versions of the evaluated algorithms are presented and their computational complexities are discussed.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114409756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
Multi-user eye tracking suitable for 3D display applications 适合3D显示应用的多用户眼动追踪
K. Hopf, F. Neumann, D. Przewozny
{"title":"Multi-user eye tracking suitable for 3D display applications","authors":"K. Hopf, F. Neumann, D. Przewozny","doi":"10.1109/3DTV.2011.5877222","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877222","url":null,"abstract":"The development of tracked 3D displays is based on real-time technologies providing precise and robust eye location detection. The paper focuses on tracking approaches which have been developed within the European HELIUM3D project. A first system uses multiple common video cameras and a second approach is combining high resolution and depth camera technology. Flexible and scalable software has been developed supporting such different hardware implementations. Beside system descriptions the paper will focus on performance evaluations which have been accomplished identifying the pros and cons of the different implementations.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114490421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
High-definition 3DTV trial service over terrestrial broadcasting network 地面广播网络高清3DTV试播服务
Gwangsoon Lee, Chan Kim, Kwang-Suh Jung, W. Cheong, N. Hur
{"title":"High-definition 3DTV trial service over terrestrial broadcasting network","authors":"Gwangsoon Lee, Chan Kim, Kwang-Suh Jung, W. Cheong, N. Hur","doi":"10.1109/3DTV.2011.5877234","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877234","url":null,"abstract":"This paper presents a three-dimensional television (3DTV) trial broadcasting service that has been recently launched in Korea. The 3DTV trial broadcasting service employs a delivery mechanism of 3D content, called as dual stream method that delivers left and right images over each encoded stream based on MPEG-2 system technology, guaranteeing backward-compatibility. Specifically, this dual stream method is regarded as a proper solution for providing higher image quality both 2D and 3D video. This paper also presents a service mechanism along with signaling method, which enables 2D and 3D service to broadcast in a time-scheduled manner. Finally, we summarize the results of high-definition (HD) 3D trial broadcasting service.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126131499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
A real-time coarse-to-fine multiview capture system for all-in-focus rendering on a light-field display 一个实时的从粗到精的多视图捕捉系统,用于光场显示器上的全聚焦渲染
F. Marton, E. Gobbetti, F. Bettio, Jose A. Iglesias-Guitian, R. Pintus
{"title":"A real-time coarse-to-fine multiview capture system for all-in-focus rendering on a light-field display","authors":"F. Marton, E. Gobbetti, F. Bettio, Jose A. Iglesias-Guitian, R. Pintus","doi":"10.1109/3DTV.2011.5877176","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877176","url":null,"abstract":"We present an end-to-end system capable of real-time capturing and displaying with full horizontal parallax high-quality 3D video contents on a cluster-driven multiprojector light-field display. The capture component is an array of low-cost USB cameras connected to a single PC. RawM-JPEG data coming fromthe software-synchronized cameras are multicast over Gigabit Ethernet to the back-end nodes of the rendering cluster, where they are decompressed and rendered. For all-in-focus rendering, view-dependent depth is estimated on the GPU using a customized multiview space-sweeping approach based on fast Census-based area matching implemented in CUDA. Realtime performance is demonstrated on a system with 18 VGA cameras and 72 SVGA rendering projectors.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"449 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121029770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
View synthesis for mixed resolution multivew 3D videos 查看合成的混合分辨率多视角3D视频
Seungsin Lee, Seok Lee, Jaejoon Lee, H. Wey
{"title":"View synthesis for mixed resolution multivew 3D videos","authors":"Seungsin Lee, Seok Lee, Jaejoon Lee, H. Wey","doi":"10.1109/3DTV.2011.5877200","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877200","url":null,"abstract":"Multiview 3D videos can efficiently be represented using a mixed resolution multiview 3D video format that has a number of color and depth information with different resolutions. However, such a mixed resolution multiview video format would have a shortcoming on synthesizing virtual views between a low and a high resolution view. This paper provides an approach to synthesize virtual image from multi-view color and depth videos whose resolutions are different from each other.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124930127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Real-time arbitrary view rendering on GPU from stereo video and time-of-flight camera 实时任意视图渲染GPU从立体视频和飞行时间的相机
Tugrul K. Ates, A. Aydin Alatan
{"title":"Real-time arbitrary view rendering on GPU from stereo video and time-of-flight camera","authors":"Tugrul K. Ates, A. Aydin Alatan","doi":"10.1109/3DTV.2011.5877214","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877214","url":null,"abstract":"Generating in-between images from multiple views of a scene is a crucial task for both computer vision and computer graphics fields. Photorealistic rendering, 3DTV and robot navigation are some of many applications which benefit from arbitrary view synthesis, if it is achieved in real-time. GPUs excel in achieving high computation power by processing arrays of data in parallel, which make them ideal for real-time computer vision applications. This paper proposes an arbitrary view rendering algorithm by using two high resolution color cameras along with a single low resolution time-of-flight depth camera and utilizing GPUs to achieve real-time processing rates. The presented ideas are examined in an experimental framework and based on the experimental results, it could be concluded that it is possible to realize content production and display stages of a free-viewpoint system in real-time by using only low-cost commodity computing devices.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123102108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
The virtual video camera: Simplified 3DTV acquisition and processing 虚拟摄像机:简化了3DTV的采集和处理
C. Lipski, F. Klose, K. Ruhl, M. Magnor
{"title":"The virtual video camera: Simplified 3DTV acquisition and processing","authors":"C. Lipski, F. Klose, K. Ruhl, M. Magnor","doi":"10.1109/3DTV.2011.5877229","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877229","url":null,"abstract":"We present the Virtual Video Camera, and end-to-end image-based free viewpoint framework. Novel spatial and temporal views are rendered from a set of unsynchronized, uncalibrated video streams. These loose requirements make outdoor recordings with consumer grade camcorders possible. Sophisticated visual effects can be devised in post-production, and stereoscopic output videos can be rendered with a variable baseline. Our Virtual Video Camera integrates seamlessly into traditional 2D and 3D post-production workflows.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125755574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Content creation for stereoscopic 3D and beyond 内容创建立体3D和超越
A. Smolic
{"title":"Content creation for stereoscopic 3D and beyond","authors":"A. Smolic","doi":"10.1109/3DTV.2011.5877148","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877148","url":null,"abstract":"2010 was the year of breakthrough for 3D video. Stereoscopic 3D is established in cinema, on Blu-ray, TV, PCs, laptops, and mobile devices. Since technology for stereo 3D is mature and content creation is understood well enough, these developments are expected to be sustainable this time. Most current systems rely on classical approaches to 3D video, i.e., representation as stereo or multiview video, coding and transmission using simulcast, frame-compatible composition or MVC. More advanced “next generation” approaches exploit some kind of understanding of the 3D scene geometry such as depth or disparity, in order to extend functionality and increase efficiency. This includes for instance flexible adjustment of depth impression to viewing conditions and user preferences or support of autostereoscopic multiview displays. Also content creation for classical stereo 3D can greatly benefit from such 3D geometry aware processing. Naturally such advanced 3D video representation formats require advanced processing algorithms, e.g., to extract 3D geometry and to render virtual views. Such advanced 3D video representation and processing will be the focus of this talk.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114864595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Planar representation for intra coding of depth maps 深度图内部编码的平面表示
M. Oguz Bici, J. Lainema, K. Ugur, M. Gabbouj
{"title":"Planar representation for intra coding of depth maps","authors":"M. Oguz Bici, J. Lainema, K. Ugur, M. Gabbouj","doi":"10.1109/3DTV.2011.5877206","DOIUrl":"https://doi.org/10.1109/3DTV.2011.5877206","url":null,"abstract":"In this paper, an intra coding method is proposed aiming to efficiently code the smooth regions in the depth map images. One of the characteristics of typical depth map images is that they contain large gradually changing smooth areas. Traditional block based transform coding algorithms are causing blocking artifacts for this type of regions. Instead of using transform coding, the proposed method utilizes piecewise linear planar representations to code the smooth areas in the depth map picture. The piecewise linear representation for a block is obtained using the already decoded pixels neighboring the block and the block's bottom-right sample. The experimental results show that significant compression improvement can be achieved with depth sequences containing smooth regions. By visual inspection, it is also shown that the blocking artifacts are significantly reduced.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114748810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信